codex — security audits

Flagged by auditors

Independent security partners scan this skill's files for malicious content, prompt injection and risky patterns. Verdicts below come from the skills.sh audit program; each partner links to its full report.

• Gen Agent Trust Hub

  fail

  This skill presents a security risk by constructing shell commands directly from user-provided input, creating a path for command injection. Additionally, it encourages the use of high-privilege sandbox modes and contains deceptive references to non-existent AI models.

  Risk: HIGHCOMMAND_EXECUTIONFeb 17, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · No issues

  Risk: MEDIUMFeb 17, 2026Full report

• Runlayer

  fail

  2/2 files flagged

  Risk: HIGHFeb 26, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report